文档 AWS SDK 示例 GitHub 存储库中还有更多 S AWS DK 示例
本文属于机器翻译版本。若本译文内容与英语原文存在差异,则一律以英文原文为准。
使用 SDK for Python (Boto3) 的 Amazon Bedrock 运行时系统示例
以下代码示例向您展示了如何使用 AWS SDK for Python (Boto3) 与 Amazon Bedrock Runtime 配合使用来执行操作和实现常见场景。
操作是大型程序的代码摘录,必须在上下文中运行。您可以通过操作了解如何调用单个服务函数,还可以通过函数相关场景和跨服务示例的上下文查看操作。
场景 是展示如何通过在同一服务中调用多个函数来完成特定任务的代码示例。
每个示例都包含一个指向的链接 GitHub,您可以在其中找到有关如何在上下文中设置和运行代码的说明。
主题
AI21 Labs 侏罗纪-2
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 AI21 Labs Jurassic-2 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 AI21 Labs Jurassic-2 发送短信。
# Use the Conversation API to send a text message to AI21 Labs Jurassic-2. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Jurassic-2 Mid. model_id = "ai21.j2-mid-v1" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. response = client.converse( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the response text. response_text = response["output"]["message"]["content"][0]["text"] print(response_text) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用于 Python 的AWS SDK 中的 Convers e (Boto3) API 参考。
-
以下代码示例展示了如何使用调用模型 API 向 AI21 Labs Jurassic-2 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用调用模型 API 发送短信。
# Use the native inference API to send a text message to AI21 Labs Jurassic-2. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Jurassic-2 Mid. model_id = "ai21.j2-mid-v1" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Format the request payload using the model's native structure. native_request = { "prompt": prompt, "maxTokens": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1) # Decode the response body. model_response = json.loads(response["body"].read()) # Extract and print the response text. response_text = model_response["completions"][0]["data"]["text"] print(response_text)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
Amazon Titan Image Generator
以下代码示例展示了如何在 Amazon Bedrock 上调用 Amazon Titan Image 来生成图像。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Amazon Titan 图像生成器创建图片。
# Use the native inference API to create an image with Amazon Titan Image Generator import base64 import boto3 import json import os import random # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Titan Image Generator G1. model_id = "amazon.titan-image-generator-v1" # Define the image generation prompt for the model. prompt = "A stylized picture of a cute old steampunk robot." # Generate a random seed. seed = random.randint(0, 2147483647) # Format the request payload using the model's native structure. native_request = { "taskType": "TEXT_IMAGE", "textToImageParams": {"text": prompt}, "imageGenerationConfig": { "numberOfImages": 1, "quality": "standard", "cfgScale": 8.0, "height": 512, "width": 512, "seed": seed, }, } # Convert the native request to JSON. request = json.dumps(native_request) # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) # Decode the response body. model_response = json.loads(response["body"].read()) # Extract the image data. base64_image_data = model_response["images"][0] # Save the generated image to a local folder. i, output_dir = 1, "output" if not os.path.exists(output_dir): os.makedirs(output_dir) while os.path.exists(os.path.join(output_dir, f"titan_{i}.png")): i += 1 image_data = base64.b64decode(base64_image_data) image_path = os.path.join(output_dir, f"titan_{i}.png") with open(image_path, "wb") as file: file.write(image_data) print(f"The generated image has been saved to {image_path}")
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
Amazon Titan 文本
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 Amazon Titan Text 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 Amazon Titan Text 发送短信。
# Use the Conversation API to send a text message to Amazon Titan Text. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Titan Text Premier. model_id = "amazon.titan-text-premier-v1:0" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. response = client.converse( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the response text. response_text = response["output"]["message"]["content"][0]["text"] print(response_text) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用于 Python 的AWS SDK 中的 Convers e (Boto3) API 参考。
-
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 Amazon Titan Text 发送短信并实时处理响应流。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 Amazon Titan Text 发送短信,并实时处理响应流。
# Use the Conversation API to send a text message to Amazon Titan Text # and print the response stream. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Titan Text Premier. model_id = "amazon.titan-text-premier-v1:0" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. streaming_response = client.converse_stream( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the streamed response text in real-time. for chunk in streaming_response["stream"]: if "contentBlockDelta" in chunk: text = chunk["contentBlockDelta"]["delta"]["text"] print(text, end="") except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用ConverseStream于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用调用模型 API 向 Amazon Titan Text 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用调用模型 API 发送短信。
# Use the native inference API to send a text message to Amazon Titan Text. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Titan Text Premier. model_id = "amazon.titan-text-premier-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Format the request payload using the model's native structure. native_request = { "inputText": prompt, "textGenerationConfig": { "maxTokenCount": 512, "temperature": 0.5, }, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1) # Decode the response body. model_response = json.loads(response["body"].read()) # Extract and print the response text. response_text = model_response["results"][0]["outputText"] print(response_text)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例演示如何使用调用模型 API 向 Amazon Titan 文本模型发送短信并打印响应流。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Invoke Model API 发送短信并实时处理响应流。
# Use the native inference API to send a text message to Amazon Titan Text # and print the response stream. import boto3 import json # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Titan Text Premier. model_id = "amazon.titan-text-premier-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Format the request payload using the model's native structure. native_request = { "inputText": prompt, "textGenerationConfig": { "maxTokenCount": 512, "temperature": 0.5, }, } # Convert the native request to JSON. request = json.dumps(native_request) # Invoke the model with the request. streaming_response = client.invoke_model_with_response_stream( modelId=model_id, body=request ) # Extract and print the response text in real-time. for event in streaming_response["body"]: chunk = json.loads(event["chunk"]["bytes"]) if "outputText" in chunk: print(chunk["outputText"], end="")
-
有关 API 的详细信息,请参阅适用InvokeModelWithResponseStream于 Python 的AWS SDK (Boto3) API 参考。
-
Amazon Titan Text Embeddings
以下代码示例展示了如何:
开始创建您的第一个嵌入内容。
创建嵌入式,配置维度数量和归一化(仅限 V2)。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Amazon Titan 文本嵌入创建您的第一个嵌入内容。
# Generate and print an embedding with Amazon Titan Text Embeddings V2. import boto3 import json # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Titan Text Embeddings V2. model_id = "amazon.titan-embed-text-v2:0" # The text to convert to an embedding. input_text = "Please recommend books with a theme similar to the movie 'Inception'." # Create the request for the model. native_request = {"inputText": input_text} # Convert the native request to JSON. request = json.dumps(native_request) # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) # Decode the model's native response body. model_response = json.loads(response["body"].read()) # Extract and print the generated embedding and the input text token count. embedding = model_response["embedding"] input_token_count = model_response["inputTextTokenCount"] print("\nYour input:") print(input_text) print(f"Number of input tokens: {input_token_count}") print(f"Size of the generated embedding: {len(embedding)}") print("Embedding:") print(embedding)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
Anthropic Claude
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 Anthropic Claude 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 Anthropic Claude 发送短信。
# Use the Conversation API to send a text message to Anthropic Claude. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Claude 3 Haiku. model_id = "anthropic.claude-3-haiku-20240307-v1:0" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. response = client.converse( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the response text. response_text = response["output"]["message"]["content"][0]["text"] print(response_text) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用于 Python 的AWS SDK 中的 Convers e (Boto3) API 参考。
-
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 Anthropic Claude 发送短信并实时处理响应流。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 Anthropic Claude 发送短信并实时处理响应流。
# Use the Conversation API to send a text message to Anthropic Claude # and print the response stream. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Claude 3 Haiku. model_id = "anthropic.claude-3-haiku-20240307-v1:0" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. streaming_response = client.converse_stream( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the streamed response text in real-time. for chunk in streaming_response["stream"]: if "contentBlockDelta" in chunk: text = chunk["contentBlockDelta"]["delta"]["text"] print(text, end="") except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用ConverseStream于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用 Invoke Model API 向 Anthropic Claude 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用调用模型 API 发送短信。
# Use the native inference API to send a text message to Anthropic Claude. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Claude 3 Haiku. model_id = "anthropic.claude-3-haiku-20240307-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Format the request payload using the model's native structure. native_request = { "anthropic_version": "bedrock-2023-05-31", "max_tokens": 512, "temperature": 0.5, "messages": [ { "role": "user", "content": [{"type": "text", "text": prompt}], } ], } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1) # Decode the response body. model_response = json.loads(response["body"].read()) # Extract and print the response text. response_text = model_response["content"][0]["text"] print(response_text)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用 Invoke Model API 向 Anthropic Claude 模型发送短信并打印响应流。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Invoke Model API 发送短信并实时处理响应流。
# Use the native inference API to send a text message to Anthropic Claude # and print the response stream. import boto3 import json # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Claude 3 Haiku. model_id = "anthropic.claude-3-haiku-20240307-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Format the request payload using the model's native structure. native_request = { "anthropic_version": "bedrock-2023-05-31", "max_tokens": 512, "temperature": 0.5, "messages": [ { "role": "user", "content": [{"type": "text", "text": prompt}], } ], } # Convert the native request to JSON. request = json.dumps(native_request) # Invoke the model with the request. streaming_response = client.invoke_model_with_response_stream( modelId=model_id, body=request ) # Extract and print the response text in real-time. for event in streaming_response["body"]: chunk = json.loads(event["chunk"]["bytes"]) if chunk["type"] == "content_block_delta": print(chunk["delta"].get("text", ""), end="")
-
有关 API 的详细信息,请参阅适用InvokeModelWithResponseStream于 Python 的AWS SDK (Boto3) API 参考。
-
Cohere Command
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 Cohere Command 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 Cohere Command 发送短信。
# Use the Conversation API to send a text message to Cohere Command. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Command R. model_id = "cohere.command-r-v1:0" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. response = client.converse( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the response text. response_text = response["output"]["message"]["content"][0]["text"] print(response_text) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用于 Python 的AWS SDK 中的 Convers e (Boto3) API 参考。
-
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 Cohere Command 发送短信并实时处理响应流。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 Cohere Command 发送短信并实时处理响应流。
# Use the Conversation API to send a text message to Cohere Command # and print the response stream. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Command R. model_id = "cohere.command-r-v1:0" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. streaming_response = client.converse_stream( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the streamed response text in real-time. for chunk in streaming_response["stream"]: if "contentBlockDelta" in chunk: text = chunk["contentBlockDelta"]["delta"]["text"] print(text, end="") except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用ConverseStream于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用调用模型 API 向 Cohere Command R 和 R+ 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用调用模型 API 发送短信。
# Use the native inference API to send a text message to Cohere Command R and R+. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Command R. model_id = "cohere.command-r-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Format the request payload using the model's native structure. native_request = { "message": prompt, "max_tokens": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1) # Decode the response body. model_response = json.loads(response["body"].read()) # Extract and print the response text. response_text = model_response["text"] print(response_text)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用调用模型 API 向 Cohere Command 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用调用模型 API 发送短信。
# Use the native inference API to send a text message to Cohere Command. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Command Light. model_id = "cohere.command-light-text-v14" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Format the request payload using the model's native structure. native_request = { "prompt": prompt, "max_tokens": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1) # Decode the response body. model_response = json.loads(response["body"].read()) # Extract and print the response text. response_text = model_response["generations"][0]["text"] print(response_text)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用带有响应流的 Invoke Model API 向 Cohere Command 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Invoke Model API 发送短信并实时处理响应流。
# Use the native inference API to send a text message to Cohere Command R and R+ # and print the response stream. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Command R. model_id = "cohere.command-r-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Format the request payload using the model's native structure. native_request = { "message": prompt, "max_tokens": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. streaming_response = client.invoke_model_with_response_stream( modelId=model_id, body=request ) # Extract and print the response text in real-time. for event in streaming_response["body"]: chunk = json.loads(event["chunk"]["bytes"]) if "generations" in chunk: print(chunk["generations"][0]["text"], end="") except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用带有响应流的 Invoke Model API 向 Cohere Command 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Invoke Model API 发送短信并实时处理响应流。
# Use the native inference API to send a text message to Cohere Command # and print the response stream. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Command Light. model_id = "cohere.command-light-text-v14" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Format the request payload using the model's native structure. native_request = { "prompt": prompt, "max_tokens": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. streaming_response = client.invoke_model_with_response_stream( modelId=model_id, body=request ) # Extract and print the response text in real-time. for event in streaming_response["body"]: chunk = json.loads(event["chunk"]["bytes"]) if "generations" in chunk: print(chunk["generations"][0]["text"], end="") except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
Meta Llama
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 Meta Llama 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 Meta Llama 发送短信。
# Use the Conversation API to send a text message to Meta Llama. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Llama 3 8b Instruct. model_id = "meta.llama3-8b-instruct-v1:0" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. response = client.converse( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the response text. response_text = response["output"]["message"]["content"][0]["text"] print(response_text) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用于 Python 的AWS SDK 中的 Convers e (Boto3) API 参考。
-
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 Meta Llama 发送短信并实时处理响应流。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 Meta Llama 发送短信并实时处理响应流。
# Use the Conversation API to send a text message to Meta Llama # and print the response stream. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Llama 3 8b Instruct. model_id = "meta.llama3-8b-instruct-v1:0" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. streaming_response = client.converse_stream( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the streamed response text in real-time. for chunk in streaming_response["stream"]: if "contentBlockDelta" in chunk: text = chunk["contentBlockDelta"]["delta"]["text"] print(text, end="") except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用ConverseStream于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用 Invoke Model API 向 Meta Llama 2 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用调用模型 API 发送短信。
# Use the native inference API to send a text message to Meta Llama 2. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Llama 2 Chat 13B. model_id = "meta.llama2-13b-chat-v1" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Embed the prompt in Llama 2's instruction format. formatted_prompt = f"<s>[INST] {prompt} [/INST]" # Format the request payload using the model's native structure. native_request = { "prompt": formatted_prompt, "max_gen_len": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1) # Decode the response body. model_response = json.loads(response["body"].read()) # Extract and print the response text. response_text = model_response["generation"] print(response_text)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用 Invoke Model API 向 Meta Llama 3 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用调用模型 API 发送短信。
# Use the native inference API to send a text message to Meta Llama 3. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Llama 3 8b Instruct. model_id = "meta.llama3-8b-instruct-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Embed the prompt in Llama 3's instruction format. formatted_prompt = f""" <|begin_of_text|> <|start_header_id|>user<|end_header_id|> {prompt} <|eot_id|> <|start_header_id|>assistant<|end_header_id|> """ # Format the request payload using the model's native structure. native_request = { "prompt": formatted_prompt, "max_gen_len": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1) # Decode the response body. model_response = json.loads(response["body"].read()) # Extract and print the response text. response_text = model_response["generation"] print(response_text)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用 Invoke Model API 向 Meta Llama 2 发送短信并打印响应流。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Invoke Model API 发送短信并实时处理响应流。
# Use the native inference API to send a text message to Meta Llama 2 # and print the response stream. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Llama 2 Chat 13B. model_id = "meta.llama2-13b-chat-v1" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Embed the prompt in Llama 2's instruction format. formatted_prompt = f"<s>[INST] {prompt} [/INST]" # Format the request payload using the model's native structure. native_request = { "prompt": formatted_prompt, "max_gen_len": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. streaming_response = client.invoke_model_with_response_stream( modelId=model_id, body=request ) # Extract and print the response text in real-time. for event in streaming_response["body"]: chunk = json.loads(event["chunk"]["bytes"]) if "generation" in chunk: print(chunk["generation"], end="") except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用InvokeModelWithResponseStream于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用 Invoke Model API 向 Meta Llama 3 发送短信并打印响应流。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Invoke Model API 发送短信并实时处理响应流。
# Use the native inference API to send a text message to Meta Llama 3 # and print the response stream. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Llama 3 8b Instruct. model_id = "meta.llama3-8b-instruct-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Embed the prompt in Llama 3's instruction format. formatted_prompt = f""" <|begin_of_text|> <|start_header_id|>user<|end_header_id|> {prompt} <|eot_id|> <|start_header_id|>assistant<|end_header_id|> """ # Format the request payload using the model's native structure. native_request = { "prompt": formatted_prompt, "max_gen_len": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. streaming_response = client.invoke_model_with_response_stream( modelId=model_id, body=request ) # Extract and print the response text in real-time. for event in streaming_response["body"]: chunk = json.loads(event["chunk"]["bytes"]) if "generation" in chunk: print(chunk["generation"], end="") except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用InvokeModelWithResponseStream于 Python 的AWS SDK (Boto3) API 参考。
-
Mistral AI
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 Mistral 发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 Mistral 发送短信。
# Use the Conversation API to send a text message to Mistral. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Mistral Large. model_id = "mistral.mistral-large-2402-v1:0" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. response = client.converse( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the response text. response_text = response["output"]["message"]["content"][0]["text"] print(response_text) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用于 Python 的AWS SDK 中的 Convers e (Boto3) API 参考。
-
以下代码示例展示了如何使用 Bedrock 的 Converse API 向 Mistral 发送短信并实时处理响应流。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Bedrock 的 Converse API 向 Mistral 发送短信并实时处理响应流。
# Use the Conversation API to send a text message to Mistral # and print the response stream. import boto3 from botocore.exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region you want to use. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Mistral Large. model_id = "mistral.mistral-large-2402-v1:0" # Start a conversation with the user message. user_message = "Describe the purpose of a 'hello world' program in one line." conversation = [ { "role": "user", "content": [{"text": user_message}], } ] try: # Send the message to the model, using a basic inference configuration. streaming_response = client.converse_stream( modelId=model_id, messages=conversation, inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9}, ) # Extract and print the streamed response text in real-time. for chunk in streaming_response["stream"]: if "contentBlockDelta" in chunk: text = chunk["contentBlockDelta"]["delta"]["text"] print(text, end="") except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用ConverseStream于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用 Invoke Model API 向 Mistral 模型发送短信。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用调用模型 API 发送短信。
# Use the native inference API to send a text message to Mistral. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Mistral Large. model_id = "mistral.mistral-large-2402-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Embed the prompt in Mistral's instruction format. formatted_prompt = f"<s>[INST] {prompt} [/INST]" # Format the request payload using the model's native structure. native_request = { "prompt": formatted_prompt, "max_tokens": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}") exit(1) # Decode the response body. model_response = json.loads(response["body"].read()) # Extract and print the response text. response_text = model_response["outputs"][0]["text"] print(response_text)
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-
以下代码示例展示了如何使用 Invoke Model API 向 Mistral AI 模型发送短信并打印响应流。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 Invoke Model API 发送短信并实时处理响应流。
# Use the native inference API to send a text message to Mistral # and print the response stream. import boto3 import json from botocore.Exceptions import ClientError # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Mistral Large. model_id = "mistral.mistral-large-2402-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Embed the prompt in Mistral's instruction format. formatted_prompt = f"<s>[INST] {prompt} [/INST]" # Format the request payload using the model's native structure. native_request = { "prompt": formatted_prompt, "max_tokens": 512, "temperature": 0.5, } # Convert the native request to JSON. request = json.dumps(native_request) try: # Invoke the model with the request. streaming_response = client.invoke_model_with_response_stream( modelId=model_id, body=request ) # Extract and print the response text in real-time. for event in streaming_response["body"]: chunk = json.loads(event["chunk"]["bytes"]) if "outputs" in chunk: print(chunk["outputs"][0].get("text"), end="") except (ClientError, Exception) as e: print(f"ERROR: Can't invoke '{model_id}''. Reason: {e}") exit(1)
-
有关 API 的详细信息,请参阅适用InvokeModelWithResponseStream于 Python 的AWS SDK (Boto3) API 参考。
-
场景
以下代码示例演示了如何创建操场,以通过不同模态与 Amazon Bedrock 基础模型交互。
- SDK for Python (Boto3)
-
Python Foundation Model (FM) Playground 是一款 Python/FastAPI 示例应用程序,演示如何将 Amazon Bedrock 与 Python 结合使用。此示例演示 Python 开发人员可如何使用 Amazon Bedrock 来构建支持生成式人工智能的应用程序。您可以使用以下三个操场测试 Amazon Bedrock 基础模型并与之交互:
-
文本操场。
-
聊天操场。
-
图像操场。
该示例还列出并显示您可以访问的基础模型及其特点。有关源代码和部署说明,请参阅中的项目GitHub
。 本示例中使用的服务
Amazon Bedrock 运行时系统
-
以下代码示例展示了如何使用 Amazon Bedrock 和 Step Functions 构建和编排生成式人工智能应用程序。
- SDK for Python (Boto3)
-
Amazon Bedrock Serverless Pro AWS Step Functionsmpt Chaining 场景演示了如何使用 A mazon B edrock 和 Amazon Bedrock 代理来构建和编排复杂、无服务器且高度可扩展的生成人工智能应用程序。它包含以下工作示例:
-
为文学博客撰写一份对给定小说的分析。此示例说明了一个简单的、按顺序排列的提示链。
-
生成有关给定主题的短篇小说。此示例说明了 AI 如何以迭代方式处理其先前生成的项目列表。
-
创建前往给定目的地的周末度假行程。此示例说明如何并行处理多个不同的提示。
-
向扮演电影制片人的人类用户推销电影创意。此示例说明了如何使用不同的推理参数对同一个提示进行并行处理,如何回溯到链中的上一个步骤,以及如何将人工输入作为工作流程的一部分。
-
根据用户手头的食材计划膳食。这个例子说明了提示链如何整合两个不同的人工智能对话,两个人工智能角色相互进行辩论以改善最终结果。
-
查找并总结当今最热门的 GitHub 存储库。此示例说明如何链接多个与外部 API 交互的 AI 代理。
有关完整的源代码以及设置和运行说明,请参阅上的完整项目GitHub
。 本示例中使用的服务
Amazon Bedrock
Amazon Bedrock 运行时系统
Agents for Amazon Bedrock
亚马逊 Bedrock Runtime 的代理
Step Functions
-
Stable Diffusion
以下代码示例展示了如何在 Amazon Bedrock 上调用 Stability.ai Stable Diffusion XL 来生成图像。
- SDK for Python (Boto3)
-
注意
还有更多相关信息 GitHub。在 AWS 代码示例存储库
中查找完整示例,了解如何进行设置和运行。 使用 “稳定扩散” 创建图像。
# Use the native inference API to create an image with Stability.ai Stable Diffusion import base64 import boto3 import json import os import random # Create a Bedrock Runtime client in the AWS Region of your choice. client = boto3.client("bedrock-runtime", region_name="us-east-1") # Set the model ID, e.g., Stable Diffusion XL 1. model_id = "stability.stable-diffusion-xl-v1" # Define the image generation prompt for the model. prompt = "A stylized picture of a cute old steampunk robot." # Generate a random seed. seed = random.randint(0, 4294967295) # Format the request payload using the model's native structure. native_request = { "text_prompts": [{"text": prompt}], "style_preset": "photographic", "seed": seed, "cfg_scale": 10, "steps": 30, } # Convert the native request to JSON. request = json.dumps(native_request) # Invoke the model with the request. response = client.invoke_model(modelId=model_id, body=request) # Decode the response body. model_response = json.loads(response["body"].read()) # Extract the image data. base64_image_data = model_response["artifacts"][0]["base64"] # Save the generated image to a local folder. i, output_dir = 1, "output" if not os.path.exists(output_dir): os.makedirs(output_dir) while os.path.exists(os.path.join(output_dir, f"stability_{i}.png")): i += 1 image_data = base64.b64decode(base64_image_data) image_path = os.path.join(output_dir, f"stability_{i}.png") with open(image_path, "wb") as file: file.write(image_data) print(f"The generated image has been saved to {image_path}")
-
有关 API 的详细信息,请参阅适用InvokeModel于 Python 的AWS SDK (Boto3) API 参考。
-